A reliable and energy‐efficient routing protocol for underwater wireless sensor networks

Recently, underwater wireless sensor networks (UWSNs) have attracted much research attention to support various applications for pollution monitoring, tsunami warnings, offshore exploration, tactical surveillance, etc. However, because of the peculiar characteristics of UWSNs, designing communication protocols for UWSNs is a challenging task. Particularly, designing a routing protocol is of the most importance for successful data transmissions between sensors and the sink. In this paper, we propose a reliable and energy‐efficient routing protocol, named R‐ERP²R (Reliable Energy‐efficient Routing Protocol based on physical distance and residual energy). The main idea behind R‐ERP²R is to utilize physical distance as a routing metric and to balance energy consumption among sensors. Furthermore, during the selection of forwarding nodes, link quality towards the forwarding nodes is also considered to provide reliability and the residual energy of the forwarding nodes to prolong network lifetime. Using the NS‐2 simulator, R‐ERP²R is compared against a well‐known routing protocol (i.e. depth‐based routing) in terms of network lifetime, energy consumption, end‐to‐end delay and delivery ratio. The simulation results proved that R‐ERP²R performs better in UWSNs.Copyright © 2012 John Wiley & Sons, Ltd.     

Ensemble Deep Learning Framework for Situational Aspects-Based Annotation and Classification of International Student’s Tweets during COVID-19

As the COVID-19 pandemic swept the globe, social media platforms became an essential source of information and communication for many. International students, particularly, turned to Twitter to express their struggles and hardships during this difficult time. To better understand the sentiments and experiences of these international students, we developed the Situational Aspect-Based Annotation and Classification (SABAC) text mining framework. This framework uses a three-layer approach, combining baseline Deep Learning (DL) models with Machine Learning (ML) models as meta-classifiers to accurately predict the sentiments and aspects expressed in tweets from our collected Student-COVID-19 dataset. Using the proposed aspect2class annotation algorithm, we labeled bulk unlabeled tweets according to their contained aspect terms. However, we also recognized the challenges of reducing data’s high dimensionality and sparsity to improve performance and annotation on unlabeled datasets. To address this issue, we proposed the Volatile Stopwords Filtering (VSF) technique to reduce sparsity and enhance classifier performance. The resulting Student-COVID Twitter dataset achieved a sophisticated accuracy of 93.21% when using the random forest as a meta-classifier. Through testing on three benchmark datasets, we found that the SABAC ensemble framework performed exceptionally well. Our findings showed that international students during the pandemic faced various issues, including stress, uncertainty, health concerns, financial stress, and difficulties with online classes and returning to school. By analyzing and summarizing these annotated tweets, decision-makers can better understand and address the real-time problems international students face during the ongoing pandemic.